BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Spicy adjectives and nominal donkeys: Capturing semantic deviance 
 using compositionality in distributional spaces - Eva Maria Vecchi\, Unive
 rsity of Trento
DTSTART:20130726T110000Z
DTEND:20130726T120000Z
UID:TALK46019@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Sophisticated senator and legislative onion. Whether or not yo
 u have ever heard of these things\, we all have some intuition that one of
  them makes much less sense than the other. In this talk\, I propose an ap
 proach to characterize semantic deviance of composite expressions using di
 stributional semantic methods\, that is\, methods to represent word and ph
 rase meaning based on the sets of contexts in which they occur in corpora.
  I present a set of simple measures extracted from distributional represen
 tations of words and phrases\, and show that they are more significant in 
 determining the acceptability of novel adjective-noun (AN) phrases than me
 asures classically employed in studies of compound processing. Our results
  show that the degree of modification an adjective has on the distribution
 al representation of a noun is the most telling factor in modelling the di
 stinction between acceptable and deviant phrases. Thus\, composition funct
 ions that are able to best estimate the degree of modification to the noun
  model human intuition of semantic acceptability with the best performance
 .
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR